Book Image

Hands-On Neural Networks

By : Leonardo De Marchi, Laura Mitchell
Book Image

Hands-On Neural Networks

By: Leonardo De Marchi, Laura Mitchell

Overview of this book

Neural networks play a very important role in deep learning and artificial intelligence (AI), with applications in a wide variety of domains, right from medical diagnosis, to financial forecasting, and even machine diagnostics. Hands-On Neural Networks is designed to guide you through learning about neural networks in a practical way. The book will get you started by giving you a brief introduction to perceptron networks. You will then gain insights into machine learning and also understand what the future of AI could look like. Next, you will study how embeddings can be used to process textual data and the role of long short-term memory networks (LSTMs) in helping you solve common natural language processing (NLP) problems. The later chapters will demonstrate how you can implement advanced concepts including transfer learning, generative adversarial networks (GANs), autoencoders, and reinforcement learning. Finally, you can look forward to further content on the latest advancements in the field of neural networks. By the end of this book, you will have the skills you need to build, train, and optimize your own neural network model that can be used to provide predictable solutions.

Related Content you might be interested in

Current Title:

Small book image
Hands-On Neural Networks
Leonardo De Marchi | Laura Mitchell
May, 2019 | 280 pages
Small book image
Deep Learning with PyTorch 1.x
Sri Yogesh Kondadasula | Vishnu Subramanian | Laura Mitchell
Nov, 2019 | 304 pages
Small book image
Python Deep Learning Cookbook
Indra den Bakker
Oct, 2017 | 330 pages
Small book image
Hands-On Neural Networks with Keras
Niloy Purkait
Mar, 2019 | 462 pages
Table of Contents (16 chapters)
Preface
Preface
Who this book is for
What this book covers
To get the most out of this book
Get in touch
Free Chapter
1
Section 1: Getting Started
Section 1: Getting Started
2
Getting Started with Supervised Learning
Getting Started with Supervised Learning
History of AI
An overview of machine learning
Environment setup
Supervised learning in practice with Python
Feature engineering
Supervised learning algorithms
Summary
3
Neural Network Fundamentals
Neural Network Fundamentals
The perceptron
Keras
Feedforward neural networks
FFNN in Python from scratch
Summary
4
Section 2: Deep Learning Applications
Section 2: Deep Learning Applications
5
Convolutional Neural Networks for Image Processing
Convolutional Neural Networks for Image Processing
Understanding CNNs
Convolutional layers
CNNs in Keras
Keras for expression recognition
Optimizing the network
Summary
6
Exploiting Text Embedding
Exploiting Text Embedding
Machine learning for NLP
Understanding word embeddings
GloVe
Summary
7
Working with RNNs
Working with RNNs
Understanding RNNs
Long Short-Term Memory
LSTMs in Keras
Summary
8
Reusing Neural Networks with Transfer Learning
Reusing Neural Networks with Transfer Learning
Transfer learning theory
Implementing MTL
Feature extraction
Implementing TL in PyTorch
Summary
9
Section 3: Advanced Applications
Section 3: Advanced Applications
10
Working with Generative Algorithms
Working with Generative Algorithms
Discriminative versus generative algorithms
Understanding GANs
GAN variations and timelines
BigGAN
StyleGAN
Deepfakes
RadialGAN
Summary
Further reading
11
Implementing Autoencoders
Implementing Autoencoders
Overview of autoencoders
Autoencoder applications
Bottleneck and loss functions
Standard types of autoencoder
Variational Autoencoders
Training VAEs
Summary
Further reading
12
Deep Belief Networks
Deep Belief Networks
Overview of DBNs
DBN architecture
Training DBNs
Fine-tuning
Datasets and libraries
Summary
Further reading
13
Reinforcement Learning
Reinforcement Learning
Basic definitions
Introducing Q-learning
Playing with OpenAI Gym
The frozen lake problem
Summary
14
Whats Next?
Whats Next?
Summarizing the book
Future of machine learning
Artificial general intelligence
Conclusions
15
Other Books You May Enjoy
Other Books You May Enjoy
Leave a review - let other readers know what you think

Optimizing the network

It would be great now to identify what we could improve in our network and also how our filters are reacting. It makes intuitive sense that it's possible to map the input pixels and understand which pixel helped determine a certain classification. This can help us understand why our model is not working correctly, as we can see which parts of the image mislead our model, and how it's possible to improve.

We will now see how it's possible to use it to further improve our network. To make it easier to understand and follow we will look at the MNIST dataset.

Let's start with a saliency map, which highlights the importance of each pixel in a classification context and can be regarded as a type of image segmentation. The map will highlight some specific areas in our image that contributed the most to the classification, as shown in the following...

Previous Section
End of Section 6
Next Section